Optimum Design of High-Order Digital Differentiator Based on neural Networks Algorithm

The optimum design approach of higher-order FIR digital differentiator based on the algorithm of neural networks was introduced in this paper. Its main idea was to minimize the sum of the square errors between the amplitude response of the ideal FIR differentiator and that of the designed by training the weight vector of neural networks, then obtaining the impulse response of FIR digital differentiator. The convergence theorem of the neural-network algorithm is presented and proved, and the optimal design approach is introduced by examples of higher-order FIR digital differentiator. The results show that the higher-order digital differentiator designed by training the weights of neural networks has very high precision and very fast convergence speed, and initial weights are random. Therefore, the presented optimum design method of higher-order FIR digital differentiator is significantly effective